WithinUsAI/Qwen3-Space.Agent.Claude.Uncensored-4B
Full fine-tune vs Qwen/Qwen3-4B-Thinking-2507. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 145/145, MLP 108/108, Attention 144/144
3 derivatives checked
- mradermacher/Qwen3.0-SpaceAgent-Claude-4B-Uncensored-GGUF: Same weights, converted
- mradermacher/Qwen3-Space.Agent.Claude-Uncensored-4B-i1-GGUF: Quantization
- mradermacher/Qwen3-Space.Agent.Claude-Uncensored-4B-GGUF: Same weights, converted